© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 3548
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and syntax commonly used in programming languages and technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uky
    -0.07
    /cmd
    -0.07
    CustomAttributes
    -0.07
     kles
    -0.07
    andler
    -0.07
    emat
    -0.07
    âķij
    -0.07
    'gc
    -0.06
    avelength
    -0.06
    stor
    -0.06
    POSITIVE LOGITS
    iram
    0.07
    marsh
    0.06
    aces
    0.06
    unction
    0.06
    ħ
    0.06
    Ī
    0.06
    ança
    0.06
    Ħ
    0.06
    ÄĽk
    0.06
    174
    0.06
    Activations Density 0.006%

    No Known Activations